Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8b9b4fa8f6a98856be2095fac98bf717c5e34b75d9e7a3aa69d2ffc069b853f
+oid sha256:4ea5e38f0c28b9fbef54b473fc520f1baae8477c6b55e26e23d3723fb4ad99da
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb43dd5888ac4bd6ea7cbc370ef770fe7253c3ab1560212d702fa60351fac1c9
+oid sha256:5f8540b08077f5ed06dcaaea899c685d08697f084c9ef1d445921fa6a9942b71
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1982d72f3f4f446cae04689c9ac92d3b920848c175c7208e6263b5cff7f25011
+oid sha256:1d1ade61a06b8f7b45fbbc92ccab3c09f2ad0350ac751391014c58b390244a53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5995034575462341,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04239533651298357,
+  "best_metric": 0.5719356536865234,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.06359300476947535,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 3.309,
       "eval_steps_per_second": 0.831,
       "step": 20
+    },
+    {
+      "epoch": 0.04451510333863275,
+      "grad_norm": 0.510029673576355,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.2456,
+      "step": 21
+    },
+    {
+      "epoch": 0.05087440381558029,
+      "grad_norm": 0.579888105392456,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.1742,
+      "step": 24
+    },
+    {
+      "epoch": 0.052994170641229466,
+      "eval_loss": 0.5767956376075745,
+      "eval_runtime": 119.5601,
+      "eval_samples_per_second": 3.329,
+      "eval_steps_per_second": 0.836,
+      "step": 25
+    },
+    {
+      "epoch": 0.057233704292527825,
+      "grad_norm": 0.5771500468254089,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.1709,
+      "step": 27
+    },
+    {
+      "epoch": 0.06359300476947535,
+      "grad_norm": 0.5936694741249084,
+      "learning_rate": 0.0,
+      "loss": 2.1232,
+      "step": 30
+    },
+    {
+      "epoch": 0.06359300476947535,
+      "eval_loss": 0.5719356536865234,
+      "eval_runtime": 118.8779,
+      "eval_samples_per_second": 3.348,
+      "eval_steps_per_second": 0.841,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.613858577416192e+16,
+  "total_flos": 3.920787866124288e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null